© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116770
    Prev
    Next
    INDEX
    Explanations

    license information or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اکث
    -0.07
     جميعا
    -0.06
     Insgesamt
    -0.06
    matric
    -0.06
     மக்களுக்கு
    -0.06
    მ
    -0.06
    对我
    -0.06
    FullPath
    -0.06
    ική
    -0.06
    同時
    -0.06
    POSITIVE LOGITS
     Please
    0.07
     如果
    0.06
     again
    0.06
     clearfix
    0.06
     गठित
    0.06
     explicitly
    0.06
     please
    0.06
     so
    0.06
     expressly
    0.05
     -
    0.05
    Activations Density 0.013%

    No Known Activations